Credit Card Fraud Detection Using State-of-the-Art Machine Learning and Deep Learning Algorithms

People can use credit cards for online transactions as it provides an efficient and easy-to-use facility. With the increase in usage of cards, capacity card misuse has also enhanced. Credit frauds cause significant financial losses both holders companies. In this research study, main aim is to detect such frauds, including accessibility public data, high-class imbalance changes fraud nature, high rates false alarm. The relevant literature presents many machines learning based approaches detection, Extreme Learning Method, Decision Tree, Random Forest, Support Vector Machine, Logistic Regression XG Boost. However, due low accuracy, there still a need apply state art deep algorithms reduce losses. focus been recent development purpose. Comparative analysis machine was performed find outcomes. detailed empirical carried out using European benchmark dataset detection. A algorithm first applied dataset, which improved accuracy detection some extent. Later, three architectures on convolutional neural network are improve performance. Further addition layers further increased comprehensive by applying variations number hidden layers, epochs latest models. evaluation work shows results achieved, f1-score, precision AUC Curves having optimized values 99.9%,85.71%,93%, 98%, respectively. proposed model outperforms state-of-the-art problems. addition, we have experiments balancing data minimize negative rate. be implemented effectively real-world fraud.